{"id":"https://openalex.org/W2070507812","doi":"https://doi.org/10.1145/1148170.1148285","title":"Term proximity scoring for ad-hoc retrieval on very large text collections","display_name":"Term proximity scoring for ad-hoc retrieval on very large text collections","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2070507812","doi":"https://doi.org/10.1145/1148170.1148285","mag":"2070507812"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033673650","display_name":"Stefan B\u00fcttcher","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Stefan B\u00fcttcher","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Charles L. A. Clarke","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073426637","display_name":"Brad Lushman","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brad Lushman","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033673650"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":24.1323,"has_fulltext":false,"cited_by_count":162,"citation_normalized_percentile":{"value":0.99325986,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998898029327393},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7777985334396362},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7391656637191772},{"id":"https://openalex.org/keywords/term-discrimination","display_name":"Term Discrimination","score":0.6474782824516296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34793275594711304},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3340802788734436},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.26084816455841064},{"id":"https://openalex.org/keywords/concept-search","display_name":"Concept search","score":0.1474836766719818},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.07311615347862244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998898029327393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7777985334396362},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7391656637191772},{"id":"https://openalex.org/C22639730","wikidata":"https://www.wikidata.org/wiki/Q7702546","display_name":"Term Discrimination","level":5,"score":0.6474782824516296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34793275594711304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3340802788734436},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.26084816455841064},{"id":"https://openalex.org/C182861755","wikidata":"https://www.wikidata.org/wiki/Q5158391","display_name":"Concept search","level":4,"score":0.1474836766719818},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.07311615347862244},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1148170.1148285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.62.29","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.29","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://stefan.buettcher.org/papers/buettcher_2006_term_proximity.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W95284390","https://openalex.org/W1482214997","https://openalex.org/W1760082936"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W1988358289","https://openalex.org/W2368472114","https://openalex.org/W2795459131","https://openalex.org/W3028990185","https://openalex.org/W2161852686","https://openalex.org/W2077948748","https://openalex.org/W2349640748","https://openalex.org/W2361661854","https://openalex.org/W2377391927"],"abstract_inverted_index":{"We":[0,52],"propose":[1],"an":[2,29],"integration":[3],"of":[4,15,32,46,61],"term":[5,62],"proximity":[6,63],"scoring":[7,64],"into":[8],"Okapi":[9],"BM25.":[10],"The":[11],"relative":[12],"retrieval":[13,17],"effectiveness":[14],"our":[16,33],"method,":[18],"compared":[19],"to":[20,26],"pure":[21],"BM25,":[22],"varies":[23],"from":[24],"collection":[25,50],"collection.We":[27],"present":[28],"experimental":[30],"evaluation":[31],"method":[34],"and":[35],"show":[36,54],"that":[37,55],"the":[38,44,47,59],"gains":[39],"achieved":[40],"over":[41],"BM25":[42],"as":[43],"size":[45],"underlying":[48],"text":[49],"increases.":[51],"also":[53],"for":[56,68],"stemmed":[57],"queries":[58],"impact":[60],"is":[65],"larger":[66],"than":[67],"unstemmed":[69],"queries.":[70]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":18}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
